Noometry

Model comparison

GPT-6 Astra vs Qwen2-72B

GPT-6 Astra is the stronger model overall, scoring 70.8 to 30.0 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-6 Astra OpenAI

70.8

Rank #1 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-6 Astra scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Astra leads 93.5 to 30.2.
  • The biggest single-benchmark swing is WeirdML: 93.6% for GPT-6 Astra and 11.3% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

GPT-6 AstraQwen2-72B
ProviderOpenAIAlibaba (Qwen)
Noometry Index70.830.0
Released2026-09-032024-06-07
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked5626

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding GPT-6 Astra leads

GPT-6 Astra: 73.7 (#2), Qwen2-72B: 29.1 (#310)

BenchmarkGPT-6 AstraQwen2-72B
WeirdML93.6%11.3%
LMArena Coding14871196
DeepSWE74.1%—
FrontierCode53.3%—
LMArena WebDev1786—
FrontierSWE65.5%—
SciCode56.5%—
GSO79.4%—
BigCodeBench Instruct—38.5%
MirrorCode46.7%—
BigCodeBench Complete—54%
ALE-Bench2,951—

Agentic & Tool Use GPT-6 Astra leads

GPT-6 Astra: 52.9 (#3), Qwen2-72B: 17.0 (#146)

BenchmarkGPT-6 AstraQwen2-72B
APEX-Agents64.7%—
Remote Labor Index20.8%—
TheAgentCompany—1.1%
BALROG68.3%—
GDP.pdf34.2%—
METR Time Horizons—29.9%
Vending-Bench 215,515—

Reasoning GPT-6 Astra leads

GPT-6 Astra: 85.1 (#1), Qwen2-72B: 23.2 (#181)

BenchmarkGPT-6 AstraQwen2-72B
LMArena Hard Prompts14621191
Epoch Capabilities Index166.45125.28
ARC-AGI-295%—
NYT Connections (extended)98.1%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles72%—
EBR-Bench76.2%—
Mystery Game Puzzles84%—
DTBench97.3%—
LMCA64.4%—
Bench to the Future 30.14—

Math GPT-6 Astra leads

GPT-6 Astra: 93.5 (#2), Qwen2-72B: 30.2 (#236)

BenchmarkGPT-6 AstraQwen2-72B
LMArena Math14651235
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 497.6%—
OTIS Mock AIME 2024-2025100%—
ProofBench99%—
MATH Level 5—39.1%
FrontierMath Erdős2.9%—

Knowledge GPT-6 Astra leads

GPT-6 Astra: 75.3 (#1), Qwen2-72B: 21.2 (#275)

BenchmarkGPT-6 AstraQwen2-72B
GPQA Diamond95.8%40.8%
LMArena Expert14831171
Humanity's Last Exam54.8%—
SimpleQA Verified75.6%—
Vectara Hallucination Rate8.7%—
MMLU—82.4%

Multimodal Not comparable

GPT-6 Astra: 55.0 (#3), Qwen2-72B: —

BenchmarkGPT-6 AstraQwen2-72B
LMArena Vision1281—
Blueprint-Bench 249.7%—
Furniture Assembly80%—
LMArena Document1468—

Multilingual GPT-6 Astra leads

GPT-6 Astra: 53.7 (#61), Qwen2-72B: 35.9 (#244)

BenchmarkGPT-6 AstraQwen2-72B
LMArena Non-English14301176
LMArena Chinese14841240
LMArena French14561170
LMArena German14401151
LMArena Japanese13791111
LMArena Korean14261083
LMArena Russian14361169
LMArena Spanish14071169

Instruction Following GPT-6 Astra leads

GPT-6 Astra: 76.3 (#44), Qwen2-72B: 61.7 (#241)

BenchmarkGPT-6 AstraQwen2-72B
LMArena Instruction Following14501181

Long Context GPT-6 Astra leads

GPT-6 Astra: 44.5 (#62), Qwen2-72B: 36.1 (#235)

BenchmarkGPT-6 AstraQwen2-72B
LMArena Longer Query14561192

Writing & Preference GPT-6 Astra leads

GPT-6 Astra: 75.3 (#7), Qwen2-72B: 40.8 (#241)

BenchmarkGPT-6 AstraQwen2-72B
LMArena Text14411203
LMArena Creative Writing14181181
LMArena Multi-Turn14481196
EQ-Bench Creative Writing2173—

Frequently asked questions

Is GPT-6 Astra better than Qwen2-72B?

GPT-6 Astra is the stronger model overall, scoring 70.8 to 30.0 on the Noometry Index.

Is GPT-6 Astra or Qwen2-72B better for coding?

GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 29.1 in the Noometry coding category.

How many benchmarks do GPT-6 Astra and Qwen2-72B share?

20 benchmarks have published results for both models. GPT-6 Astra has 56 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper